List your company

Question Answering on Jeopardy

34.7AccuracyEnsemble
26.06828.30930.5532.791Jun 17, 2025

Evaluation results

MethodLinks
EnsembleAggregation Method=Byte-level Ensemble2025.0634.7
OLMO2Model=OLMO22025.0632.7
AverageAggregation Method=Average2025.0628.8
QWEN3Model=QWEN32025.0627.4
LLAMA3.2Model=LLAMA3.22025.0626.4